Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achen
    -0.17
    SqlParameter
    -0.15
     Ramos
    -0.15
    acht
    -0.14
    ACHE
    -0.13
    ÑĤÑİ
    -0.13
    禮
    -0.13
    rosso
    -0.13
    system
    -0.13
    ework
    -0.13
    POSITIVE LOGITS
    entin
    0.20
    tÃŃ
    0.17
    endance
    0.15
     exp
    0.14
    cake
    0.14
    etur
    0.14
     tÃŃ
    0.13
    ¹
    0.13
     Brock
    0.13
    /doc
    0.13
    Act Density 0.253%

    No Known Activations